mlpc-lab

/

BLIVA_Vicuna

Like 5

Follow

mlpc-ucsd 10

This pull request completely revamps the model card for this repository to accurately reflect the ESTR-CoT model, as described in the paper ESTR-CoT: Towards Explainable and Accurate Event Stream based Scene Text Recognition with Chain-of-Thought Reasoning.

The update includes:

• Replacing all outdated information related to the previous BLIVA model with details about ESTR-CoT.
• Setting the pipeline_tag to image-text-to-text to better categorize the model on the Hub, making it discoverable for visual-to-text tasks.
• Confirming the library_name as transformers based on the model's components (Llama tokenizer, Vicuna-7B).
• Adding license: cc-by-nc-4.0, a common non-commercial license, as a placeholder until an official license is released with the code.